Add exclusions CSS selectors

This is needed if there are selector that match in elements that should be excluded from the index.
DeuxHuitHuit · Mar 29, 2018 · 366718e · 366718e
1 parent 247295f
commit 366718e
Show file tree

Hide file tree

Showing 5 changed files with 37 additions and 2 deletions.
diff --git a/README.md b/README.md
@@ -167,6 +167,20 @@ CSS selector for the title of the page.
 
 CSS selector for the "key" property. You can add custom keys as you wish.
 
+### exclusions: Object
+
+An object containing CSS selectors to find elements that must not be indexed.
+Those CSS selectors are matched for each node and are check against all their parents to make
+sure non of its parent are excluded.
+
+#### exclusions.text: String
+
+CSS selector of excluded elements for the text of the page.
+
+#### exclusions[key]: String
+
+CSS selector of excluded elements for "key" property. The key must match the one used in selectors[key].
+
 #### formatters: Object
 
 An object containing formatter string. Their values are removed from the original result obtained

diff --git a/app.js b/app.js
@@ -59,7 +59,8 @@ config.selectors = _.map(config.selectors, (selector, key) => {
 	return {
 		key,
 		attributes: selector.attributes,
-		selector: selector.selector
+		selector: selector.selector,
+		exclude: config.exclusions && config.exclusions[key]
 	};
 });
 

diff --git a/config.json b/config.json
@@ -29,6 +29,9 @@
 		"image": "meta[property=\"og:image\"]",
 		"description": "meta[name=\"description\"]",
 		"text": "h1, h2, h3, h4, h5, h6, p, li"
+	},
+	"exclusions": {
+
 	},
 	"formatters": {
 		"title": "-"

diff --git a/lib/process.js b/lib/process.js
@@ -87,7 +87,11 @@ const parse = (record, data, config) => {
 		const key = selector.key;
 		if (record[key] === undefined) {
 			record[key] = [];
-			const nodes = $(selector.selector);
+			// Fetch all and filter exclusions
+			const nodes = $(selector.selector).filter((i, node) => {
+				return !selector.exclude || $(node).closest(selector.exclude).length === 0;
+			});
+
 			// Populate the record
 			_.each(nodes, (node) => recursiveFindValue(node, record[key], selector.attributes));
 

diff --git a/test/parse.js b/test/parse.js
@@ -43,6 +43,19 @@ test('Custom selector parse', (t) => {
 	t.end();
 });
 
+test('Selector exclusion parse', (t) => {
+	const rec = {};
+	const c = _.clone(config);
+	const data = `<html><body>
+	<a>test</a>
+	<footer><a class="no-ok">not-ok</a></footer>
+</body></html>`;
+	c.selectors.push({key: 'links', selector: 'a', exclude: 'footer'});
+	parse(rec, data, c);
+	t.equal(rec.links, 'test');
+	t.end();
+});
+
 test('JSON formatter', (t) => {
 	const rec = {};
 	const c = _.clone(config);